BWhat changed
Developed a masked-encoder forecasting architecture for heterogeneous frequencies, variable numbers of channels and varying output distributions, trained on the accompanying LOTSA time-series collection.
Scientific scope
Developed a masked-encoder forecasting architecture for heterogeneous frequencies, variable numbers of channels and varying output distributions, trained on the accompanying LOTSA time-series collection. Universal is a modeling objective, not a guarantee for every time series. Transformer and masked modeling are inherited; reported zero-shot results are bounded to evaluated datasets. Later Moirai-MoE/2 releases are distinct follow-up leads, not silently included.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Universal is a modeling objective, not a guarantee for every time series. Transformer and masked modeling are inherited; reported zero-shot results are bounded to evaluated datasets. Later Moirai-MoE/2 releases are distinct follow-up leads, not silently included.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Unified Training of Universal Time Series Forecasting Transformers
- Woo et al.: Moirai unified variable-dimensional forecasting — author/institution implementation
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction